Differentially Private Linear Bandits with Partial Distributed Feedback
Differentially Private Linear Bandits with Partial Distributed Feedback
复制标题
DOI：
10.23919/wiopt56218.2022.9930524
复制
发表时间：
2022-07
期刊：
影响因子：
--
通讯作者：
Fengjiao Li;Xingyu Zhou;Bo Ji
中科院分区：
文献类型：
--
作者：
Fengjiao Li;Xingyu Zhou;Bo Ji
在本文中，我们仅通过部分分布式反馈来研究全球奖励最大化的问题。为了解决这个问题，我们考虑了不同的私人分布线性匪徒，其中只选择了一部分来自人群的用户（称为客户）参加学习过程，而中央服务器通过迭代的私人属于私人的phor，从而从迭代的部分中学习了这种部分反馈。 （DP-DPE）可以自然地与流行的差异隐私（DP）模型（包括中央DP，本地DP和Shuffle DP），我们证明，DP-DPE既可以享受sumblenear的遗憾，又可以保证simper offie offie offie ofer-dpe。证实我们的理论结果并证明了DP-DPE的有效性。
In this paper, we study the problem of global reward maximization with only partial distributed feedback. This problem is motivated by several real-world applications (e.g., cellular network configuration, dynamic pricing, and policy selection) where an action taken by a central entity influences a large population that contributes to the global reward. However, collecting such reward feedback from the entire population not only incurs a prohibitively high cost, but often leads to privacy concerns. To tackle this problem, we consider differentially private distributed linear bandits, where only a subset of users from the population are selected (called clients) to participate in the learning process and the central server learns the global model from such partial feedback by iteratively aggregating these clients’ local feedback in a differentially private fashion. We then propose a unified algorithmic learning framework, called differentially private distributed phased elimination (DP-DPE), which can be naturally integrated with popular differential privacy (DP) models (including central DP, local DP, and shuffle DP). Furthermore, we prove that DP-DPE achieves both sublinear regret and sublinear communication cost. Interestingly, DP-DPE also achieves privacy protection “for free” in the sense that the additional cost due to privacy guarantees is a lower-order additive term. Finally, we conduct simulations to corroborate our theoretical results and demonstrate the effectiveness of DP-DPE.